Update training logs at step 1600

training_logs.jsonl

@@ -50,3 +50,20 @@
 {"step": 1175, "epoch": 0.9506472491909385, "time": "2026-06-26 20:33:22", "logs": {"loss": 0.19982004165649414, "grad_norm": 3.2695255279541016, "learning_rate": 1.886965553444568e-05, "epoch": 0.9506472491909385}}
 {"step": 1200, "epoch": 0.970873786407767, "time": "2026-06-26 20:33:45", "logs": {"loss": 0.22285139083862304, "grad_norm": 19.842267990112305, "learning_rate": 1.8786767152368197e-05, "epoch": 0.970873786407767}}
 {"step": 1200, "epoch": 0.970873786407767, "time": "2026-06-26 20:34:20", "logs": {"eval_loss": 0.14106644690036774, "eval_accuracy": 0.9641232945932289, "eval_precision": 0.9650485436893204, "eval_recall": 0.9887267904509284, "eval_f1": 0.9767441860465116, "eval_runtime": 34.6101, "eval_samples_per_second": 57.18, "eval_steps_per_second": 3.583, "epoch": 0.970873786407767}}
+{"step": 1225, "epoch": 0.9911003236245954, "time": "2026-06-26 20:35:02", "logs": {"loss": 0.13252583503723145, "grad_norm": 17.05675506591797, "learning_rate": 1.8701141752722966e-05, "epoch": 0.9911003236245954}}
+{"step": 1250, "epoch": 1.0113268608414239, "time": "2026-06-26 20:35:25", "logs": {"loss": 0.13512847900390626, "grad_norm": 14.713388442993164, "learning_rate": 1.8612806007233382e-05, "epoch": 1.0113268608414239}}
+{"step": 1275, "epoch": 1.0315533980582525, "time": "2026-06-26 20:35:48", "logs": {"loss": 0.15763619422912598, "grad_norm": 16.86681365966797, "learning_rate": 1.8521787431876954e-05, "epoch": 1.0315533980582525}}
+{"step": 1300, "epoch": 1.051779935275081, "time": "2026-06-26 20:36:11", "logs": {"loss": 0.18742298126220702, "grad_norm": 0.6122269630432129, "learning_rate": 1.8428114378314237e-05, "epoch": 1.051779935275081}}
+{"step": 1325, "epoch": 1.0720064724919094, "time": "2026-06-26 20:36:33", "logs": {"loss": 0.16315383911132814, "grad_norm": 6.803472995758057, "learning_rate": 1.8331816025057508e-05, "epoch": 1.0720064724919094}}
+{"step": 1350, "epoch": 1.0922330097087378, "time": "2026-06-26 20:36:57", "logs": {"loss": 0.1462923812866211, "grad_norm": 3.42342209815979, "learning_rate": 1.823292236838186e-05, "epoch": 1.0922330097087378}}
+{"step": 1375, "epoch": 1.1124595469255663, "time": "2026-06-26 20:37:20", "logs": {"loss": 0.2096657371520996, "grad_norm": 6.770485877990723, "learning_rate": 1.813146421298154e-05, "epoch": 1.1124595469255663}}
+{"step": 1400, "epoch": 1.132686084142395, "time": "2026-06-26 20:37:42", "logs": {"loss": 0.1903732681274414, "grad_norm": 6.892830848693848, "learning_rate": 1.802747316237454e-05, "epoch": 1.132686084142395}}
+{"step": 1425, "epoch": 1.1529126213592233, "time": "2026-06-26 20:38:05", "logs": {"loss": 0.22764249801635741, "grad_norm": 1.7113957405090332, "learning_rate": 1.792098160905829e-05, "epoch": 1.1529126213592233}}
+{"step": 1450, "epoch": 1.1731391585760518, "time": "2026-06-26 20:38:28", "logs": {"loss": 0.08850884437561035, "grad_norm": 0.2954396903514862, "learning_rate": 1.7812022724419624e-05, "epoch": 1.1731391585760518}}
+{"step": 1475, "epoch": 1.1933656957928802, "time": "2026-06-26 20:38:50", "logs": {"loss": 0.15286758422851562, "grad_norm": 1.2150897979736328, "learning_rate": 1.7700630448402125e-05, "epoch": 1.1933656957928802}}
+{"step": 1500, "epoch": 1.2135922330097086, "time": "2026-06-26 20:39:13", "logs": {"loss": 0.14677520751953124, "grad_norm": 2.9238908290863037, "learning_rate": 1.758683947893406e-05, "epoch": 1.2135922330097086}}
+{"step": 1525, "epoch": 1.2338187702265373, "time": "2026-06-26 20:39:36", "logs": {"loss": 0.13224196434020996, "grad_norm": 9.288032531738281, "learning_rate": 1.747068526112022e-05, "epoch": 1.2338187702265373}}
+{"step": 1550, "epoch": 1.2540453074433657, "time": "2026-06-26 20:39:59", "logs": {"loss": 0.08127058982849121, "grad_norm": 21.540422439575195, "learning_rate": 1.735220397620101e-05, "epoch": 1.2540453074433657}}
+{"step": 1575, "epoch": 1.2742718446601942, "time": "2026-06-26 20:40:22", "logs": {"loss": 0.10571711540222167, "grad_norm": 0.07893255352973938, "learning_rate": 1.7231432530282246e-05, "epoch": 1.2742718446601942}}
+{"step": 1600, "epoch": 1.2944983818770226, "time": "2026-06-26 20:40:44", "logs": {"loss": 0.1872186279296875, "grad_norm": 0.5910708904266357, "learning_rate": 1.7108408542839146e-05, "epoch": 1.2944983818770226}}
+{"step": 1600, "epoch": 1.2944983818770226, "time": "2026-06-26 20:41:19", "logs": {"eval_loss": 0.1455843597650528, "eval_accuracy": 0.9671551288529561, "eval_precision": 0.9737360472751149, "eval_recall": 0.98342175066313, "eval_f1": 0.9785549323655559, "eval_runtime": 34.8064, "eval_samples_per_second": 56.857, "eval_steps_per_second": 3.563, "epoch": 1.2944983818770226}}